🌔 moondream1

1.6B parameter model built by @vikhyatk using SigLIP, Phi-1.5 and the LLaVa training dataset. The model is release for research purposes only, commercial use is not allowed.

Try it out on Huggingface Spaces! Or check out the moondream repository on GitHub for inference code and other details.

Benchmarks

Model	Parameters	VQAv2	GQA	VizWiz	TextVQA
LLaVA-1.5	13.3B	80.0	63.3	53.6	61.3
LLaVA-1.5	7.3B	78.5	62.0	50.0	58.2
MC-LLaVA-3B	3B	64.2	49.6	24.9	38.6
LLaVA-Phi	3B	71.4	-	35.9	48.6
moondream1	1.6B	74.3	56.3	30.3	39.8

Examples

Image	Examples
	What is the title of this book? The Little Book of Deep Learning What can you tell me about this book? The book appears to be a white booklet titled "The Little Book of Deep Learning." It is held in a person's hand, and it seems to be a personal possession. The book's content focuses on the basics of deep learning, which is a field of artificial intelligence that uses neural networks to process and analyze data. It is likely that the book provides an introduction to the concepts and techniques involved in deep learning, making it accessible for beginners and helping them understand the fundamentals of this advanced machine learning approach. Where is the person standing? The person is standing on a balcony or a deck, which is located outside the house.
	What type of food is the girl holding? The girl is holding a large hamburger or burger, which is a type of sandwich made from ground meat, typically consisting of a beef patty, and is usually served between two slices of bread. What color is the woman's hair? The woman's hair is white. What is the girl doing in the image? The girl in the image is eating a hamburger.
	What color is the train? The train is red. What is the bus doing in the image? The bus is driving down a street, passing through an intersection, and traveling on a train track. What kind of public transportation is in the image? The image features a red trolley or commuter train on a city street, which is a form of public transportation.
	What is the girl looking at? The girl is looking at her reflection in the mirror while adjusting her uniform. What color is the woman's hair? The woman's hair is brown. What is the woman doing in the mirror? The woman is adjusting her hair in the mirror.
	What might be the reason for the dog's aggressive behavior? The dog's aggressive behavior, with its teeth bared and growling, could be due to several reasons. It is possible that the dog is feeling threatened, scared, or defensive in its current environment, such as a room with a person it doesn't know well or a situation that provokes it. Alternatively, the dog might be reacting to a perceived threat or discomfort from the person holding it. It is essential to assess the situation and the dog's body language to determine the exact cause of its aggressive behavior and respond accordingly to ensure the safety and well-being of both the dog and the person involved. What kind of dog is in the picture? The picture features a small dog, possibly a Chihuahua, with red eyes and a mean, hungry-looking expression. What color is the dog? The dog is black and white.